Engram is a retrieval system of meaning, saving both HBM storage and bandwidth
teortaxesTex · x · 2026-09-22
Thread on DeepSeek's Engram: bookwormengr explains Engram/N-gram is not a computational system but a retrieval system of meaning (embeddings); its real benefit is not just 40-50% HBM storage savings but HBM bandwidth, which is even more expensive. teortaxesTx notes everyone wants to expand sparse memory to 80% of parametric volume, which seems hard with such impoverished but performant representations.
Related event: DeepSeek Engram Is Semantic Retrieval, Can Cut HBM Needs 40-50%(4 posts)→
More from Infra
- Cloudflare Talk: Swapping Some Agent LLM Calls for Fast Models Like Jev Gives Big Speedups — michellechen · 2026-11-12
- Cloudflare Trains Its Own Clef and Clairic Models to Complete Its Agent Stack — michellechen · 2026-11-12
- AWS open-sources 23 production-ready GenAI assets, cutting build time from months to weeks — AWS ML Blog · 2026-11-12
- Sixth Street CEO: ~$200B of Chips Sitting in Warehouses as Data Centers Lag Behind — SumitGup · 2026-11-12
- AWS CEO Matt Garman: Space Data Centers Are 10-20 Years Away, Likely Not Economically Feasible — rohanpaul_ai · 2026-11-12
- CoreWeave Database Goes GA: Managed PostgreSQL Running Inside Your CKS Cluster Next to GPUs — _ScottCondron · 2026-11-12